Files in this item



application/pdf9812517.pdf (4MB)Restricted to U of Illinois
(no description provided)PDF


Title:A Hybrid Connectionist-Instance Model of Recognition Memory
Author(s):Adams, David Russell
Doctoral Committee Chair(s):Dell, Gary S.
Department / Program:Psychology
Degree Granting Institution:University of Illinois at Urbana-Champaign
Subject(s):Psychology, Cognitive
Abstract:While connectionist models have been proposed and met with some success in many areas of psychology, connectionist models of memory have not met the standards created by competing models of memory. Much of the reason for this failure is due to the severe interference connectionist models typically show for information learned sequentially, which is often called catastrophic interference. Solutions to the catastrophic interference problem in turn sacrifice the properties that make these models attractive. This dissertation proposes an alternative connectionist model of recognition memory, which contains a solution to the catastrophic interference problem that preserves the strengths of the connectionist approach. This model not only solves the catastrophic interference problem, but proposes a unique solution to the need for models of recognition to explain both interference and generalization processes in memory.
Issue Date:1997
Description:110 p.
Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 1997.
Other Identifier(s):(MiAaPQ)AAI9812517
Date Available in IDEALS:2015-09-25
Date Deposited:1997

This item appears in the following Collection(s)

Item Statistics